695 listed
Models
Language models for agents: hosted models with input and output prices per million tokens from OpenRouter (read daily; prices change often), and open-weights models from Hugging Face with license and downloads. Filter by tool calling, context window and price, or switch to the table to compare.
Showing 193–216 of 500
- 0.577score
Skyfall 36B V2
TheDrummer
Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent…
ModelAFreshness: A$0.55 / $0.833K ctxOpen weights - 0.577score
Step 3.7 Flash
StepFun
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model.
ModelAFreshness: A$0.2 / $1.15262K ctxOpen weights - 0.577score
Step 5 Preview
StepFun
Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters).
ModelAFreshness: A$1 / $2.71M ctxOpen weights - 0.577score
Ternary Bonsai 2 27B
PrismML
Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B.
ModelAFreshness: A$0.075 / $0.5262K ctxOpen weights - 0.577score
UI-TARS 7B
ByteDance
UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games.
ModelAFreshness: A$0.1 / $0.2128K ctxOpen weights - 0.577score
Uncensored
Venice
Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with…
ModelAFreshness: A$0.2 / $0.9128K ctxOpen weights - 0.577score
UnslopNemo 12B
TheDrummer
UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.
ModelAFreshness: A$0.4 / $0.41M ctxOpen weights - 0.574score
MythoMax 13B
MythoMax 13B
One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay.
ModelAFreshness: A$0.08 / $0.118K ctxOpen weights - 0.574score
ReMM SLERP 13B
ReMM SLERP 13B
A recreation trial of the original MythoMax-L2-B13 but with updated models.
ModelAFreshness: A$0.35 / $0.656K ctxOpen weights - 0.568score
K2-Horizon-7B
IFM
Open-weights 9B-parameter text model from IFM on Hugging Face (apache-2.0).
ModelAFreshness: AOpen weights - 0.568score
Youtu-LLM-2B
tencent
Open-weights 1.96B-parameter text model from tencent on Hugging Face (youtu-llm).
ModelAFreshness: AOpen weights - 0.553score
bloom
bigscience
Open-weights 176.25B-parameter text model from bigscience on Hugging Face (bigscience-bloom-rail-1.0).
ModelBFreshness: BOpen weights - 0.553score
K-EXAONE-236B-A23B
LGAI-EXAONE
Open-weights 237.1B-parameter text model from LGAI-EXAONE on Hugging Face (k-exaone).
ModelBFreshness: BOpen weights - 0.553score
KAT-Coder-V2.5-Dev
Kwaipilot
Open-weights 34.66B-parameter text model from Kwaipilot on Hugging Face (apache-2.0).
ModelBFreshness: BOpen weights - 0.553score
LFM2-1.2B
LiquidAI
Open-weights 1.17B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelBFreshness: BOpen weights - 0.553score
LFM2.5-230M
LiquidAI
Open-weights 0.23B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelBFreshness: BOpen weights - 0.553score
LFM2.5-350M
LiquidAI
Open-weights 0.35B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelBFreshness: BOpen weights - 0.553score
LFM2.5-8B-A1B
LiquidAI
Open-weights 8.47B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelBFreshness: BOpen weights - 0.553score
Qwen3.8-27B-DFlash2
z-lab
Open-weights 1.92B-parameter text model from z-lab on Hugging Face (apache-2.0).
ModelBFreshness: BOpen weights - 0.553score
Spark-X2.5-4B
XHToken
Open-weights 4.11B-parameter text model from XHToken on Hugging Face (apache-2.0).
ModelBFreshness: BOpen weights - 0.551score
Agents-A1
InternScience
Open-weights 35.11B-parameter text model from InternScience on Hugging Face (apache-2.0).
ModelBFreshness: BOpen weights - 0.547score
LFM2-2.6B-Exp
LiquidAI
Open-weights 2.57B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelBFreshness: BOpen weights - 0.547score
LFM2.5-1.2B-Thinking
LiquidAI
Open-weights 1.17B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelBFreshness: BOpen weights - 0.547score
Ling-1T
inclusionAI
Open-weights 999.71B-parameter text model from inclusionAI on Hugging Face (mit).
ModelBFreshness: BOpen weights